Real-time dictation
Hold the pill in Transcribe mode for responsive local speech to text. Text injects into the focused field via clipboard — the overlay never steals focus.
A FUSE INTELLIGENCE PRODUCT · v1.0.18
Private Local Speech to Text & AI Notes
VocalFuse
A Fuse Intelligence subscription for local AI transcription and note taking — hold the pill to dictate into any app, click for Pro note-taking sessions, or run Continuous mode in the background. Audio never leaves your PC.
On-device transcription model (~57 MB) · Stored under C:\VocalFuse\models\ · From $5/mo
<100msAvg dictation latency
~57 MBtranscription model on disk
$5–10Monthly plans
100% localAudio stays on-device
Windows 10+
Offline after model download
No meeting bot
Speech to text at desk speed
Hold the pill, speak, release — text lands in Slack, Word, VS Code, or any focused window. VocalFuse runs a local transcription model on your CPU — no cloud speech API, no per-minute billing. Professional dictation with auto-punctuation for everyday writing.
- ✓ Always-on-top pill widget (Windows 10+) with live visualizer
- ✓ Hold-to-speak Transcribe mode — paste at cursor into any app
- ✓ Pro Note Taking — click to start/stop, AI summaries
- ✓ Pro Continuous — 60-second background clips, stays local
- ✓ Optional Account → Notes sync and Gmail summaries (Pro)
Always-on-top pill · drag grip to reposition
The VocalFuse desktop UI
Pixel-accurate replicas of the Windows client from VocalFuse_cpp — 248×38 pill overlay, six capture states, settings dialog, and system tray menu.
Pill overlay — all states
Idle
Hold to speak
Border #c4a04a · “Hold to speak”
Note ready
Click for notes
Note switch on · “Click for notes”
Recording
Border #e2c06a · 16-bar visualizer
Busy
Working...
Border #3d72c9 · “Working...”
Note taking
Pro note-taking · live meters
Note sending
Sending notes...
SMTP summary dispatch · “Sending notes...”
Settings dialog
460px panel with Product License, Note Taking Mode (email SMTP), and Updates — matching settings.cpp.
Settings
Vocal Fuse
Product License
Required to use Vocal Fuse.
VF-7K2M-9QPL-4XHN
Product key verified.
Note Taking Mode
Record continuously in 3-minute segments until stopped.
Email Delivery
Sent via SMTP when a note session ends.
notes@company.com
smtp.company.com
587
smtp-user
••••••••••••
Updates
Compare your installed version with the latest release.
Installed1.0.18
Latest1.0.18
You are up to date.
Control layout
Right-side controls: 36×16 note switch, settings gear, close button. Hover states shown below.
Hover — settings
Hold to speak
Hover — close
Hold to speak
System tray
Tray context menu: Settings, Minimize, Show, Close — from tray.cpp.
Layout reference: Pill body
#161616, accent #5ba3f5, bright border #98C0EF, drag grip 18px, logo 18px, Segoe UI labels. See the full wireframes in VocalFuse docs.
How VocalFuse works
Subscribe on the web, install the desktop client, activate with your product key, and dictate anywhere.
Subscribe
Pick Basic ($5) or Pro ($10) on the pricing page. Stripe handles billing — cancel anytime.
Download & install
Grab the installer from Downloads. First launch downloads the transcription model (~57 MB) into C:\VocalFuse\models\ if needed.
Activate & configure
Paste your product key from Product Keys, choose a recording mode, and drag the pill where you want it. Transcribe works without a key; Pro modes unlock after verification.
Dictate & capture
Hold the pill for dictation or click for Pro Note Taking and Continuous. Review synced sessions at Account → Notes — toggle cloud sync and email delivery in Account Settings.
Built for professionals who can't send voice to the cloud
Local transcription model
A ~57 MB model is downloaded once and stored on your PC. Fast, accurate dictation without a cloud speech API.
Note Taking mode (Pro)
Click to start, click to stop. VocalFuse transcribes meetings, calls, and videos locally, builds an AI summary, syncs text to Account → Notes, and can email it via Gmail.
Continuous mode (Pro)
Background listening checks 60-second clips for important moments. Bullets stay on your PC — Continuous does not sync to Account → Notes.
Privacy by architecture
Microphone audio never leaves your machine. License checks use HTTPS; voice data does not.
Developer-friendly
License verification API, architecture docs, and local AI guides for teams embedding Fuse intelligence.
Basic vs Pro
| Feature | Basic — $5/mo | Pro — $10/mo |
|---|---|---|
| Local on-device dictation | ✓ | ✓ |
| Always-on-top pill widget | ✓ | ✓ |
| Hold-to-speak dictation (Transcribe) | ✓ | ✓ |
| Product key & app updates | ✓ | ✓ |
| Note Taking — AI summaries (click start/stop) | — | ✓ |
| Continuous mode (60-second clips, local) | — | ✓ |
| Cloud notes sync (Account → Notes) | — | ✓ |
| Optional Gmail summary delivery | — | ✓ |
Who uses VocalFuse?
Developers & writers
Dictate commits, docs, and emails without leaving the IDE. The local transcription model handles everyday technical vocabulary on capable hardware.
Legal & healthcare
Keep sensitive conversations on-device. No third-party transcription bot joins your calls — audio stays in your trust boundary.
Students & creators
Capture lectures and meetings with Note Taking mode. Pro syncs transcriptions to your account and can email summaries.
System requirements
| Operating system | Windows 10/11 (64-bit) |
|---|---|
| Memory | 16 GB RAM recommended while the transcription model is loaded |
| CPU | 4-core minimum; 8+ cores recommended for snappier note batches |
| Storage | ~57 MB for the local transcription model |
| Model path | C:\VocalFuse\models\ |
| Permissions | Microphone; optional accessibility APIs for text injection |
| Account | Active VocalFuse subscription for downloads and license validation |
Need tuning advice? Read the Local AI Guide for GPU setup, or the full VocalFuse documentation for install and troubleshooting.
Start dictating in minutes
Create your account, subscribe, download VocalFuse.exe, and hold the pill to dictate. Compare Otter alternatives, Windows Voice Typing, or ask questions in the community forum.